Skip to main content
Glama
thenavidm

ScrapeCreators MCP Server

by thenavidm

Find Social Profiles

creator_tools_find_social_profiles

Find linked social profiles and same-handle accounts for a creator across Instagram, TikTok, YouTube, X/Twitter, and Facebook from a platform and handle.

Instructions

Accepts a supported platform and creator handle, validates both using platform-specific rules, and constructs the canonical source profile URL internally. URLs are not accepted as handles. Supported platforms are Instagram, TikTok, YouTube, X/Twitter, and Facebook; X is accepted as an alias for Twitter. YouTube accepts handles and 24-character channel IDs. The endpoint returns social profiles explicitly linked from the source profile and expands recognized link-in-bio pages. It also re-scrapes up to three supported profiles explicitly linked by the source and follows up to three unique public website URLs declared by the source or those trusted profiles for one page, while preserving each declared path and query. Generic service-provider landing pages reached through parked or unconfigured branded-domain redirects are ignored so the provider's own footer links are not attributed to the creator. It also checks whether the same handle exists on the other supported platforms. All attempted same-handle URLs are returned in same_handle_candidate_urls even when they cannot be verified strongly enough for profiles. Same-handle accounts are included in profiles only when corroborated by a shared owner-controlled website or a reciprocal profile link; matching handles and display names alone are not identity proof. same_handle_match records supporting name evidence at 0.75 confidence, while shared_website and website_link use 0.9. A bounded Google search discovers alternate handles, but Google results are never returned without verification. At most two candidates per other supported platform, up to four total, are re-scraped through that platform's profile scraper. The endpoint may also follow up to two unique recognized link-in-bio URLs declared by the re-scraped Google candidates. The global two-page cap is applied after candidates whose returned handles do not match their Google URLs are rejected. Optional profile probes and page fetches make one attempt and receive the shared enrichment abort signal. A reciprocal source-profile link found there verifies the candidate, and the page's explicit cross-platform profiles can then expand the verified identity graph. Google URLs that re-scrape to the same returned platform handle are deduplicated. A different-handle candidate is accepted only when it links back to the source profile, or when its normalized display name matches and it declares the same owner-controlled public website; common multi-tenant profile and storefront hosts are excluded from shared-website identity evidence. Google discovery uses google_search_match at 0.6, exact names use display_name_match at 0.75, reciprocal links use 0.95, and cross-platform social links explicitly declared by a verified candidate use verified_profile_link at 0.95. Source-linked URLs and failures are returned in source_linked_profile_urls and failed_source_linked_profile_urls. Google candidate URLs, candidate-declared link-in-bio URLs, verified URLs, and failures are returned in google_candidate_urls, google_candidate_link_in_bio_urls, verified_google_candidate_urls, failed_google_candidate_urls, and failed_google_candidate_link_in_bio_urls. Results are deterministic and do not use AI. Mixed or unreachable enrichment results are reported through partial and the matching failure fields. If every declared link-in-bio page fails and no other enrichment finds a profile, the request returns an uncharged 503. A successful live lookup costs 10 credits. Potentially consumes paid API credits; requires confirm=true. Read-like POST requests do not publish to social platforms.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
handleYesCreator handle without a profile URL. A leading @ is optional.
accountNoNamed private ScrapeCreators account; selects credentials, not a remote account ID.
confirmNoMust be true for the specific approved credit-consuming research call.
platformYesSource social platform
cache_max_ageNoIf we have a response in the cache that is this many days old or newer, return the cached response (0 credits, with "cached": true and a "cached_at" timestamp). Otherwise, scrape a live result (10 credits). [See the Caching page for details.](https://docs.scrapecreators.com/caching)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

A4.2/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Far exceeds the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false) by disclosing credit cost, caching tiers, the uncharged 503 failure path, deterministic non-AI execution, partial-result reporting, confidence thresholds per evidence type (0.75/0.9/0.6/0.95), and all the re-scrape/page caps. This is exactly the behavioral depth a caller needs before spending credits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded correctly, but the body is an enormous run-on specification enumerating internal mechanics, field names, and confidence scores across many dense sentences. Much of the signal is real, yet the length is disproportionate to selection and invocation needs and lacks structure or prioritization.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and a highly complex operation, the description compensates by naming the return fields (profiles, same_handle_candidate_urls, source_linked_profile_urls, failed_*, google_candidate_*, verified_google_candidate_urls, partial) and the failure modes. An agent has enough to call it correctly and interpret the outcome.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents handle, account, confirm, platform, and cache_max_age, making 3 the baseline. The description does add marginal value over the schema — it clarifies that a cited URL is rejected as a handle, that X is an accepted alias for twitter (explaining the duplicate enum entries), and that YouTube accepts 24-character channel IDs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource+scope: accepts a supported platform and creator handle, validates them, constructs the canonical source profile URL, and returns linked social profiles across platforms. The cross-platform discovery scope is unmistakably distinct from the single-platform profile siblings (instagram_profile, tiktok_profile, facebook_profile), even though none are named.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

States clear prerequisites and context: the handle must not be a URL, confirm=true is required for this specific credit-consuming call, a live lookup costs 10 credits versus 0 for a cache hit, and a total enrichment failure returns an uncharged 503. It never explicitly names when to prefer a single-platform sibling instead, so it stops short of true when/when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools